Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Multi-layered greedy network-growing algorithm: extension of greedy network-growing algorithm to multi-layered

Ryotaro Kamimura1

  • 1Information Science Laboratory, Tokai University, 1117 Kitakaname Hiratsuka Kanagawa 259-1292, Japan. ryo@cc.u-tokai.ac.jp

International Journal of Neural Systems
|March 23, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Collective mutual information maximization to unify passive and positive approaches for improving interpretation and generalization.

Neural networks : the official journal of the International Neural Network Society·2017
Same author

Cooperation-controlled learning for explicit class structure in self-organizing maps.

TheScientificWorldJournal·2014
Same author

Self-enhancement learning: target-creating learning and its application to self-organizing maps.

Biological cybernetics·2011
Same author

Selective information enhancement learning for creating interpretable representations in competitive learning.

Neural networks : the official journal of the International Neural Network Society·2011
Same author

Cooperative information maximization with Gaussian activation functions for self-organizing maps.

IEEE transactions on neural networks·2006
Same author

Unifying cost and information in information-theoretic competitive learning.

Neural networks : the official journal of the International Neural Network Society·2005

This study introduces an efficient network-growing algorithm for multi-layered networks, outperforming single-layered approaches on complex tasks like image analysis and medical data processing.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Single-layered networks struggle with complex problems.
  • Network-growing algorithms offer a potential solution.
  • Teacher-directed learning enhances network performance.

Purpose of the Study:

  • Extend a greedy network-growing algorithm to multi-layered networks.
  • Improve problem-solving capabilities beyond single-layered networks.
  • Enhance efficiency and accuracy using teacher-directed learning.

Main Methods:

  • Developed a greedy network-growing algorithm for multi-layered networks.
  • Integrated teacher-directed learning to minimize output errors.
  • Applied information maximization for salient feature extraction.

Related Experiment Videos

Main Results:

  • The algorithm successfully solved complex problems intractable for single-layered networks.
  • Demonstrated effectiveness in vertical-horizontal line detection, medical data analysis, and road classification.
  • Confirmed the efficiency and accuracy of the proposed network-growing method.

Conclusions:

  • Multi-layered networks with the enhanced algorithm solve complex problems effectively.
  • The algorithm provides an efficient solution for network construction and learning.
  • Information maximization aids in extracting crucial features from input data.